© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 176210
    Prev
    Next
    INDEX
    Explanations

    Titanic event or details

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_20_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rece
    0.47
    ান্তরে
    0.45
    endrá
    0.43
    ;)
    0.43
     Cumm
    0.42
    tiene
    0.42
    Trying
    0.42
    renc
    0.41
     tierras
    0.41
    ');//
    0.41
    POSITIVE LOGITS
     tijdens
    0.43
    onance
    0.43
    ましょう
    0.43
     aikana
    0.42
    она
    0.40
     بالاتر
    0.40
    віч
    0.39
    植物
    0.38
     }}{\
    0.38
    ループ
    0.38
    Activations Density 0.000%

    No Known Activations